list_browsing_tasks
AI agents call list_browsing_tasks to retrieve information from Yutori MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Listing operations retrieve data without side effects. Given the context of a web monitoring and research platform, this tool likely returns metadata about browsing tasks (status, results, history) rather than modifying state. The absence of mutation verbs (create, delete, edit, update) confirms Read classification. Severity is low because listing data poses minimal risk even if queried extensively by an AI agent.
From the tool's definition Tool name 'list_browsing_tasks' indicates a listing/retrieval operation with no modification capability. Sibling tools show clear patterns: 'get_*' and 'list_*' are read-only, while 'create_*', 'delete_*', and 'edit_*' perform mutations.
Attacks that exploit this kind of access
list_browsing_tasks. It is categorised as a Read tool in the Yutori MCP MCP Server, which means it retrieves data without modifying state.
Register the Yutori MCP server in PolicyLayer and add a rule for list_browsing_tasks: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yutori MCP. Nothing to install.
list_browsing_tasks is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_browsing_tasks rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_browsing_tasks. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_browsing_tasks is provided by the Yutori MCP server (yutori-ai/yutori-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
list_browsing_tasks is one line of Yutori's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →